From 68d686e6af0fc192fce1788f67bbe0c21a5419ab Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 22 Jun 2018 10:49:35 -0500 Subject: grep.c: expose {,inverted} match column in match_line() When calling match_line(), callers presently cannot determine the relative offset of the match because match_line() discards the 'regmatch_t' that contains this information. Instead, teach match_line() to take in two 'ssize_t's. Fill the first with the offset of the match produced by the given expression. If extended, fill the later with the offset of the match produced as if --invert were given. For instance, matching "--not -e x" on this line produces a columnar offset of 0, (i.e., the whole line does not contain an x), but "--invert --not -e -x" will fill the later ssize_t of the column containing an "x", because this expression is semantically equivalent to "-e x". To determine the column for the inverted and non-inverted case, do the following: - If matching an atom, the non-inverted column is as given from match_one_pattern(), and the inverted column is unset. - If matching a --not, the inverted column and non-inverted column swap. - If matching an --and, or --or, the non-inverted column is the minimum of the two children. Presently, the existing short-circuiting logic for AND and OR applies as before. This will change in the following commit when we add options to configure the --column flag. Taken together, this and the forthcoming change will always yield the earlier column on a given line. This patch will become useful when we later pick between the two new results in order to display the column number of the first match on a line with --column. Co-authored-by: Jeff King Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- grep.c | 58 +++++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 39 insertions(+), 19 deletions(-) (limited to 'grep.c') diff --git a/grep.c b/grep.c index 45ec7e636c..dedfe17f93 100644 --- a/grep.c +++ b/grep.c @@ -1248,11 +1248,11 @@ static int match_one_pattern(struct grep_pat *p, char *bol, char *eol, return hit; } -static int match_expr_eval(struct grep_expr *x, char *bol, char *eol, - enum grep_context ctx, int collect_hits) +static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x, char *bol, + char *eol, enum grep_context ctx, ssize_t *col, + ssize_t *icol, int collect_hits) { int h = 0; - regmatch_t match; if (!x) die("Not a valid grep expression"); @@ -1261,25 +1261,39 @@ static int match_expr_eval(struct grep_expr *x, char *bol, char *eol, h = 1; break; case GREP_NODE_ATOM: - h = match_one_pattern(x->u.atom, bol, eol, ctx, &match, 0); + { + regmatch_t tmp; + h = match_one_pattern(x->u.atom, bol, eol, ctx, + &tmp, 0); + if (h && (*col < 0 || tmp.rm_so < *col)) + *col = tmp.rm_so; + } break; case GREP_NODE_NOT: - h = !match_expr_eval(x->u.unary, bol, eol, ctx, 0); + /* + * Upon visiting a GREP_NODE_NOT, col and icol become swapped. + */ + h = !match_expr_eval(opt, x->u.unary, bol, eol, ctx, icol, col, + 0); break; case GREP_NODE_AND: - if (!match_expr_eval(x->u.binary.left, bol, eol, ctx, 0)) + if (!match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col, + icol, 0)) return 0; - h = match_expr_eval(x->u.binary.right, bol, eol, ctx, 0); + h = match_expr_eval(opt, x->u.binary.right, bol, eol, ctx, col, + icol, 0); break; case GREP_NODE_OR: if (!collect_hits) - return (match_expr_eval(x->u.binary.left, - bol, eol, ctx, 0) || - match_expr_eval(x->u.binary.right, - bol, eol, ctx, 0)); - h = match_expr_eval(x->u.binary.left, bol, eol, ctx, 0); + return (match_expr_eval(opt, x->u.binary.left, bol, eol, + ctx, col, icol, 0) || + match_expr_eval(opt, x->u.binary.right, bol, + eol, ctx, col, icol, 0)); + h = match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col, + icol, 0); x->u.binary.left->hit |= h; - h |= match_expr_eval(x->u.binary.right, bol, eol, ctx, 1); + h |= match_expr_eval(opt, x->u.binary.right, bol, eol, ctx, col, + icol, 1); break; default: die("Unexpected node type (internal error) %d", x->node); @@ -1290,25 +1304,30 @@ static int match_expr_eval(struct grep_expr *x, char *bol, char *eol, } static int match_expr(struct grep_opt *opt, char *bol, char *eol, - enum grep_context ctx, int collect_hits) + enum grep_context ctx, ssize_t *col, + ssize_t *icol, int collect_hits) { struct grep_expr *x = opt->pattern_expression; - return match_expr_eval(x, bol, eol, ctx, collect_hits); + return match_expr_eval(opt, x, bol, eol, ctx, col, icol, collect_hits); } static int match_line(struct grep_opt *opt, char *bol, char *eol, + ssize_t *col, ssize_t *icol, enum grep_context ctx, int collect_hits) { struct grep_pat *p; - regmatch_t match; if (opt->extended) - return match_expr(opt, bol, eol, ctx, collect_hits); + return match_expr(opt, bol, eol, ctx, col, icol, + collect_hits); /* we do not call with collect_hits without being extended */ for (p = opt->pattern_list; p; p = p->next) { - if (match_one_pattern(p, bol, eol, ctx, &match, 0)) + regmatch_t tmp; + if (match_one_pattern(p, bol, eol, ctx, &tmp, 0)) { + *col = tmp.rm_so; return 1; + } } return 0; } @@ -1763,6 +1782,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle while (left) { char *eol, ch; int hit; + ssize_t col = -1, icol = -1; /* * look_ahead() skips quickly to the line that possibly @@ -1786,7 +1806,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle if ((ctx == GREP_CONTEXT_HEAD) && (eol == bol)) ctx = GREP_CONTEXT_BODY; - hit = match_line(opt, bol, eol, ctx, collect_hits); + hit = match_line(opt, bol, eol, &col, &icol, ctx, collect_hits); *eol = ch; if (collect_hits) -- cgit v1.3-5-g9baa From 017c0fcfdb21dd44e2c83f533e9a6d78513e7d8c Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 22 Jun 2018 10:49:39 -0500 Subject: grep.[ch]: extend grep_opt to allow showing matched column To support showing the matched column when calling 'git-grep(1)', teach 'grep_opt' the normal set of options to configure the default behavior and colorization of this feature. Now that we have opt->columnnum, use it to disable short-circuiting over ORs and ANDs so that col and icol are always filled with the earliest matches on each line. In addition, don't return the first match from match_line(), for the same reason. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- grep.c | 47 +++++++++++++++++++++++++++++++++++++---------- grep.h | 2 ++ 2 files changed, 39 insertions(+), 10 deletions(-) (limited to 'grep.c') diff --git a/grep.c b/grep.c index dedfe17f93..c885101017 100644 --- a/grep.c +++ b/grep.c @@ -46,6 +46,7 @@ void init_grep_defaults(void) color_set(opt->color_filename, ""); color_set(opt->color_function, ""); color_set(opt->color_lineno, ""); + color_set(opt->color_columnno, ""); color_set(opt->color_match_context, GIT_COLOR_BOLD_RED); color_set(opt->color_match_selected, GIT_COLOR_BOLD_RED); color_set(opt->color_selected, ""); @@ -155,6 +156,7 @@ void grep_init(struct grep_opt *opt, const char *prefix) opt->extended_regexp_option = def->extended_regexp_option; opt->pattern_type_option = def->pattern_type_option; opt->linenum = def->linenum; + opt->columnnum = def->columnnum; opt->max_depth = def->max_depth; opt->pathname = def->pathname; opt->relative = def->relative; @@ -164,6 +166,7 @@ void grep_init(struct grep_opt *opt, const char *prefix) color_set(opt->color_filename, def->color_filename); color_set(opt->color_function, def->color_function); color_set(opt->color_lineno, def->color_lineno); + color_set(opt->color_columnno, def->color_columnno); color_set(opt->color_match_context, def->color_match_context); color_set(opt->color_match_selected, def->color_match_selected); color_set(opt->color_selected, def->color_selected); @@ -1277,23 +1280,36 @@ static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x, char *bol, 0); break; case GREP_NODE_AND: - if (!match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col, - icol, 0)) - return 0; - h = match_expr_eval(opt, x->u.binary.right, bol, eol, ctx, col, + h = match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col, icol, 0); + if (h || opt->columnnum) { + /* + * Don't short-circuit AND when given --column, since a + * NOT earlier in the tree may turn this into an OR. In + * this case, see the below comment. + */ + h &= match_expr_eval(opt, x->u.binary.right, bol, eol, + ctx, col, icol, 0); + } break; case GREP_NODE_OR: - if (!collect_hits) + if (!(collect_hits || opt->columnnum)) { + /* + * Don't short-circuit OR when given --column (or + * collecting hits) to ensure we don't skip a later + * child that would produce an earlier match. + */ return (match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col, icol, 0) || match_expr_eval(opt, x->u.binary.right, bol, eol, ctx, col, icol, 0)); + } h = match_expr_eval(opt, x->u.binary.left, bol, eol, ctx, col, icol, 0); - x->u.binary.left->hit |= h; + if (collect_hits) + x->u.binary.left->hit |= h; h |= match_expr_eval(opt, x->u.binary.right, bol, eol, ctx, col, - icol, 1); + icol, collect_hits); break; default: die("Unexpected node type (internal error) %d", x->node); @@ -1316,6 +1332,7 @@ static int match_line(struct grep_opt *opt, char *bol, char *eol, enum grep_context ctx, int collect_hits) { struct grep_pat *p; + int hit = 0; if (opt->extended) return match_expr(opt, bol, eol, ctx, col, icol, @@ -1325,11 +1342,21 @@ static int match_line(struct grep_opt *opt, char *bol, char *eol, for (p = opt->pattern_list; p; p = p->next) { regmatch_t tmp; if (match_one_pattern(p, bol, eol, ctx, &tmp, 0)) { - *col = tmp.rm_so; - return 1; + hit |= 1; + if (!opt->columnnum) { + /* + * Without --column, any single match on a line + * is enough to know that it needs to be + * printed. With --column, scan _all_ patterns + * to find the earliest. + */ + break; + } + if (*col < 0 || tmp.rm_so < *col) + *col = tmp.rm_so; } } - return 0; + return hit; } static int match_next_pattern(struct grep_pat *p, char *bol, char *eol, diff --git a/grep.h b/grep.h index 399381c908..08a0b391c5 100644 --- a/grep.h +++ b/grep.h @@ -127,6 +127,7 @@ struct grep_opt { int prefix_length; regex_t regexp; int linenum; + int columnnum; int invert; int ignore_case; int status_only; @@ -159,6 +160,7 @@ struct grep_opt { char color_filename[COLOR_MAXLEN]; char color_function[COLOR_MAXLEN]; char color_lineno[COLOR_MAXLEN]; + char color_columnno[COLOR_MAXLEN]; char color_match_context[COLOR_MAXLEN]; char color_match_selected[COLOR_MAXLEN]; char color_selected[COLOR_MAXLEN]; -- cgit v1.3-5-g9baa From 89252cd069d4acf1c6c407f00c7a1cc2c6ad3953 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 22 Jun 2018 10:49:42 -0500 Subject: grep.c: display column number of first match To prepare for 'git grep' learning '--column', teach grep.c's show_line() how to show the column of the first match on non-context lines. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- grep.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) (limited to 'grep.c') diff --git a/grep.c b/grep.c index c885101017..83fe32a6a0 100644 --- a/grep.c +++ b/grep.c @@ -1405,7 +1405,7 @@ static int next_match(struct grep_opt *opt, char *bol, char *eol, } static void show_line(struct grep_opt *opt, char *bol, char *eol, - const char *name, unsigned lno, char sign) + const char *name, unsigned lno, ssize_t cno, char sign) { int rest = eol - bol; const char *match_color, *line_color = NULL; @@ -1440,6 +1440,17 @@ static void show_line(struct grep_opt *opt, char *bol, char *eol, output_color(opt, buf, strlen(buf), opt->color_lineno); output_sep(opt, sign); } + /* + * Treat 'cno' as the 1-indexed offset from the start of a non-context + * line to its first match. Otherwise, 'cno' is 0 indicating that we are + * being called with a context line. + */ + if (opt->columnnum && cno) { + char buf[32]; + xsnprintf(buf, sizeof(buf), "%"PRIuMAX, (uintmax_t)cno); + output_color(opt, buf, strlen(buf), opt->color_columnno); + output_sep(opt, sign); + } if (opt->color) { regmatch_t match; enum grep_context ctx = GREP_CONTEXT_BODY; @@ -1545,7 +1556,7 @@ static void show_funcname_line(struct grep_opt *opt, struct grep_source *gs, break; if (match_funcname(opt, gs, bol, eol)) { - show_line(opt, bol, eol, gs->name, lno, '='); + show_line(opt, bol, eol, gs->name, lno, 0, '='); break; } } @@ -1610,7 +1621,7 @@ static void show_pre_context(struct grep_opt *opt, struct grep_source *gs, while (*eol != '\n') eol++; - show_line(opt, bol, eol, gs->name, cur, sign); + show_line(opt, bol, eol, gs->name, cur, 0, sign); bol = eol + 1; cur++; } @@ -1809,6 +1820,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle while (left) { char *eol, ch; int hit; + ssize_t cno; ssize_t col = -1, icol = -1; /* @@ -1874,7 +1886,18 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle show_pre_context(opt, gs, bol, eol, lno); else if (opt->funcname) show_funcname_line(opt, gs, bol, lno); - show_line(opt, bol, eol, gs->name, lno, ':'); + cno = opt->invert ? icol : col; + if (cno < 0) { + /* + * A negative cno indicates that there was no + * match on the line. We are thus inverted and + * being asked to show all lines that _don't_ + * match a given expression. Therefore, set cno + * to 0 to suggest the whole line matches. + */ + cno = 0; + } + show_line(opt, bol, eol, gs->name, lno, cno + 1, ':'); last_hit = lno; if (opt->funcbody) show_function = 1; @@ -1903,7 +1926,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle /* If the last hit is within the post context, * we need to show this line. */ - show_line(opt, bol, eol, gs->name, lno, '-'); + show_line(opt, bol, eol, gs->name, lno, col + 1, '-'); } next_line: -- cgit v1.3-5-g9baa From 6653fec3bb969d8be3987cf77654c0aa1778b6b5 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Fri, 22 Jun 2018 10:49:49 -0500 Subject: grep.c: add configuration variables to show matched option To support git-grep(1)'s new option, '--column', document and teach grep.c how to interpret relevant configuration options, similar to those associated with '--line-number'. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- Documentation/config.txt | 5 +++++ Documentation/git-grep.txt | 3 +++ grep.c | 6 ++++++ 3 files changed, 14 insertions(+) (limited to 'grep.c') diff --git a/Documentation/config.txt b/Documentation/config.txt index 58fde4daea..e4cbed3078 100644 --- a/Documentation/config.txt +++ b/Documentation/config.txt @@ -1183,6 +1183,8 @@ color.grep.:: function name lines (when using `-p`) `lineNumber`;; line number prefix (when using `-n`) +`column`;; + column number prefix (when using `--column`) `match`;; matching text (same as setting `matchContext` and `matchSelected`) `matchContext`;; @@ -1797,6 +1799,9 @@ gitweb.snapshot:: grep.lineNumber:: If set to true, enable `-n` option by default. +grep.column:: + If set to true, enable the `--column` option by default. + grep.patternType:: Set the default matching behavior. Using a value of 'basic', 'extended', 'fixed', or 'perl' will enable the `--basic-regexp`, `--extended-regexp`, diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt index 31dc0392a6..0de3493b80 100644 --- a/Documentation/git-grep.txt +++ b/Documentation/git-grep.txt @@ -44,6 +44,9 @@ CONFIGURATION grep.lineNumber:: If set to true, enable `-n` option by default. +grep.column:: + If set to true, enable the `--column` option by default. + grep.patternType:: Set the default matching behavior. Using a value of 'basic', 'extended', 'fixed', or 'perl' will enable the `--basic-regexp`, `--extended-regexp`, diff --git a/grep.c b/grep.c index 83fe32a6a0..992673fe7e 100644 --- a/grep.c +++ b/grep.c @@ -96,6 +96,10 @@ int grep_config(const char *var, const char *value, void *cb) opt->linenum = git_config_bool(var, value); return 0; } + if (!strcmp(var, "grep.column")) { + opt->columnnum = git_config_bool(var, value); + return 0; + } if (!strcmp(var, "grep.fullname")) { opt->relative = !git_config_bool(var, value); @@ -112,6 +116,8 @@ int grep_config(const char *var, const char *value, void *cb) color = opt->color_function; else if (!strcmp(var, "color.grep.linenumber")) color = opt->color_lineno; + else if (!strcmp(var, "color.grep.column")) + color = opt->color_columnno; else if (!strcmp(var, "color.grep.matchcontext")) color = opt->color_match_context; else if (!strcmp(var, "color.grep.matchselected")) -- cgit v1.3-5-g9baa